Legio: Fault Resiliency for Embarrassingly Parallel MPI Applications

TL;DR

Legio simplifies adding fault resiliency to embarrassingly parallel MPI applications by transparently integrating ULFM, enabling continued execution after node failures with minimal overhead and scalability impact.

Contribution

Legio provides a transparent, non-intrusive framework that hides ULFM complexity, facilitating fault resiliency in MPI applications without requiring code modifications.

Findings

Negligible overhead introduced by Legio on large-scale MPI runs

Legio maintains MPI scalability despite fault recovery features

Successful integration and fault injection testing on real-world applications

Abstract

Due to the increasing size of HPC machines, the fault presence is becoming an eventuality that applications must face. Natively, MPI provides no support for the execution past the detection of a fault, and this is becoming more and more constraining. With the introduction of ULFM (User Level Fault Mitigation library), it has been provided with a possible way to overtake a fault during the application execution at the cost of code modifications. ULFM is intrusive in the application and requires also a deep understanding of its recovery procedures. In this paper we propose Legio, a framework that lowers the complexity of introducing resiliency in an embarrassingly parallel MPI application. By hiding ULFM behind the MPI calls, the library is capable to expose resiliency features to the application in a transparent manner thus removing any integration effort. Upon fault, the failed nodes are discarded and the execution continues only with the non-failed ones. A hierarchical implementation of the solution has been also proposed to reduce the overhead of the repair process when scaling towards a large number of nodes. We evaluated our solutions on the Marconi100 cluster at CINECA, showing that the overhead introduced by the library is negligible and it does not limit the scalability properties of MPI. Moreover, we also integrated the solution in real-world applications to further prove its robustness by injecting faults.